Models

Gemini 3 Pro Image

gemini-3-pro-image-previewGoogle's most advanced image generation model.

Per image

~$0.137

Typical 1024px image; billed at the provider's actual cost for the size and quality used.

Uptime · 24h

—

No traffic yet

Playground

Input

Enter to generate · Shift+Enter for a new line

Image references · optional, edits or guides the image
Example·1408×768·18.2s·$0.1367

Example prompt: Editorial architectural photograph of a contemporary neighborhood storefront at blue hour, glowing warmly against the dusk. Above the entrance, a warm-white neon sign in flowing hand-bent cursive reads exactly "UltraGPT", the only text in the scene. Large windows reveal a cozy, lamp-lit interior with shelves of plants and books.

Details

Type
Images
Input
text, image
Output
image
Context
65,536 tokens
Aspect ratios
1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9
Resolutions
1K, 2K, 4K
Seed
No
Reference images
up to 14

Supported parameters

promptsizenresponse_formataspect_ratioresolutionimage

Last 24 hours

Requests per hour; red = provider errors.

Avg latency
—
Avg first token
—
Throughput
—

Use it

curl https://api.ultragpt.pro/v1/images/generations \
  -H "Authorization: Bearer $ULTRAGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "model": "gemini-3-pro-image-preview", "prompt": "A lighthouse at dawn, watercolor", "response_format": "url" }'

More Google models

All Gemini API models and prices

FAQ

How much does the Gemini 3 Pro Image API cost?

~$0.137 per image. You pay per use from a prepaid balance - no subscription, and every response reports its exact cost in usage.cost.

How do I call Gemini 3 Pro Image through the API?

Create an UltraGPT API key, point the official OpenAI SDK (or any OpenAI-compatible client) at https://api.ultragpt.pro/v1 and pass "gemini-3-pro-image-preview" as the model.

What is the context window of Gemini 3 Pro Image?

Gemini 3 Pro Image accepts up to 65,536 tokens of context on UltraGPT.